EUVIMEDEUVIMED entdecken
Crossref

Robust Underactuated Point-Feet Bipedal Locomotion Using Deep Reinforcement Learning and a Balance Recovery System

Aref Amiri, Soroush Zare, Mojtaba Sharifi

ASME Letters in Dynamic Systems and Control · 01.10.2025 · 5 (4)

DOI: 10.1115/1.4069223 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ASME Letters in Dynamic Systems and Control, online erschienen am 14.08.2025. Verfasst von Aref Amiri und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 29 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes a deep reinforcement learning control strategy using the twin delayed deep deterministic algorithm for the robust locomotion of a point-feet, underactuated bipedal robot. We introduce two key contributions: a specialized balance recovery system and a bioinspired reward function. The balance recovery system is explicitly trained to handle off-balance and fall-like conditions. Its effectiveness was validated through 50 randomized trials, where it achieved a 74% success rate in stabilizing the robot from a wide range of initial heights, velocities, and configurations. The bioinspired reward function encourages the robot’s hip to remain between its feet, which was shown to significantly improve the gait stability. This reward shaping reduced the normalized fluctuation in joint angle movements by a factor of 1.75, even under external disturbances. The final controller produced an average running speed of 2.4 m/s and demonstrated robustness to external disturbances of up to ±60N⋅m, paving the way for more resilient and adaptive bipedal locomotion.

Zitieren

APA

Amiri, A., Zare, S., & Sharifi, M. (2025). Robust Underactuated Point-Feet Bipedal Locomotion Using Deep Reinforcement Learning and a Balance Recovery System. ASME Letters in Dynamic Systems and Control, 5(4). https://doi.org/10.1115/1.4069223

Vancouver

Amiri A, Zare S, Sharifi M. Robust Underactuated Point-Feet Bipedal Locomotion Using Deep Reinforcement Learning and a Balance Recovery System. ASME Letters in Dynamic Systems and Control. 2025;5(4). doi:10.1115/1.4069223

BibTeX
@article{Amiri2025,
  author = {Amiri, Aref and Zare, Soroush and Sharifi, Mojtaba},
  title = {Robust Underactuated Point-Feet Bipedal Locomotion Using Deep Reinforcement Learning and a Balance Recovery System},
  journal = {ASME Letters in Dynamic Systems and Control},
  year = {2025},
  volume = {5},
  number = {4},
  doi = {10.1115/1.4069223}
}
Kostenlos starten →